6 papers
G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation
Hojun Song, Chae-yeong Song, Jeong-hun Hong +5
Point cloud segmentation is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only feature…
PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes
Christina Ourania Tze, Daniel Dauner, Yiyi Liao +2
Existing approaches to 3D semantic urban scene generation predominantly rely on voxel-based representations, which are bound by fixed resolution, challenging to edit, and memory-in…
123D: Unifying Multi-Modal Autonomous Driving Data at Scale
Daniel Dauner, Valentin Charraut, Bastian Berle +10
The pursuit of autonomous driving has produced one of the richest sensor data collections in all of robotics. However, its scale and diversity remain largely untapped. Each dataset…
Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
Jiaxin Huang, Yuanbo Yang, Bangbang Yang +3
We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reco…
InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
Shuai Yang, Hao Li, Bin Wang +7
To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often s…
Orientation Matters: Making 3D Generative Models Orientation-Aligned
Yichong Lu, Yuzhuo Tian, Zijin Jiang +7
Humans intuitively perceive object shape and orientation from a single image, guided by strong priors about canonical poses. However, existing 3D generative models often produce mi…